Legal claims defining the scope of protection. Each claim is shown in both the original legal language and a plain English translation.
1. A method for automated segmentation of a segment of a blood vessel of a subject in a medical image comprising volumetric data, comprising: segmenting circular components in parallel planes of the volumetric data in an entire medical image scan of at least one body part containing one or more blood vessels; and for each of the circular components, identifying corresponding circular components from the circular components in adjacent planes to define a contiguous segment of corresponding circular components spanning a plurality of the planes; wherein the contiguous segment defines a segment of a blood vessel.
2. The method of claim 1 wherein the corresponding circular components are defined by a maximal overlap of the circular components.
This invention relates to a method for defining circular components in a technical or geometric context, particularly where overlapping circular shapes are involved. The method addresses the challenge of precisely determining the boundaries of circular components when multiple circles intersect or overlap, ensuring accurate representation and analysis in applications such as computer-aided design, manufacturing, or geometric modeling. The method involves identifying a set of circular components that intersect or overlap with one another. For each pair or group of overlapping circles, the method calculates the maximal overlap region, which is the largest area where all circles in the group intersect. This maximal overlap is then used to define the corresponding circular component, ensuring that the resulting shape accurately represents the shared region without ambiguity. By focusing on the maximal overlap, the method avoids inconsistencies that may arise from arbitrary boundary selections, providing a standardized approach to defining circular components in overlapping scenarios. This is particularly useful in applications where precise geometric definitions are critical, such as in CAD systems, simulation models, or manufacturing templates. The method ensures that the defined circular components are both accurate and reproducible, improving reliability in downstream processes.
3. The method of claim 1 wherein the corresponding circular components are defined by closeness of the center of mass of the circular components.
This invention relates to a method for analyzing and processing circular components within an image or dataset, particularly in applications such as pattern recognition, object detection, or image segmentation. The problem addressed is the accurate identification and grouping of circular shapes based on their spatial relationships, which is challenging due to variations in size, position, and potential overlaps. The method involves defining circular components within the dataset and then determining their corresponding relationships based on the closeness of their centers of mass. By calculating the center of mass for each circular component, the method establishes a metric for proximity, allowing for the grouping or pairing of circles that are spatially close. This approach improves the accuracy of circular component analysis by reducing false positives and ensuring that related circles are correctly associated. The method may also include preprocessing steps to enhance the detection of circular components, such as noise reduction or edge enhancement, to improve the reliability of the center of mass calculations. Additionally, the method can be applied iteratively to refine the grouping of circular components, ensuring that the final output accurately represents the spatial relationships within the dataset. This technique is particularly useful in fields such as medical imaging, industrial inspection, or autonomous navigation, where precise circular object detection is critical.
4. The method of claim 1 wherein the medical image is a CT scan and wherein the circular components are identified from the intersection of a wide HU range and a narrow HU range.
This invention relates to medical imaging, specifically analyzing CT scans to identify circular components within the image. The problem addressed is the accurate detection of circular structures in CT scans, which is challenging due to variations in tissue density and noise. The solution involves analyzing the image using two different Hounsfield Unit (HU) ranges—a wide range to capture a broad spectrum of densities and a narrow range to refine the detection. The intersection of these ranges helps isolate circular components by filtering out non-circular or irrelevant structures. The method enhances the precision of identifying circular features, such as blood vessels, tumors, or other anatomical structures, by leveraging the combined information from both HU ranges. This approach improves the reliability of automated or semi-automated medical image analysis, aiding in diagnosis and treatment planning. The technique is particularly useful in applications requiring high accuracy, such as vascular imaging or tumor detection, where distinguishing circular structures from surrounding tissues is critical. By refining the detection process through dual-range HU analysis, the method reduces false positives and improves the overall diagnostic utility of CT scans.
5. A method for semi-automated identification of a seed for segmentation of a blood vessel of a head and neck of a subject in a medical image wherein the image comprises a plurality of slices, the method comprising: automatically identifying anatomical landmarks and a plurality of landmark slices containing each of the anatomical landmarks in the medical image; automatically identifying relevant landmark slices for finding the blood vessel based on positional relationships of the landmarks and the blood vessel; and manually identifying the seed for the blood vessel from within a set of slices that is constrained to the relevant landmark slices.
This invention relates to medical imaging and the automated identification of a seed point for segmenting blood vessels in the head and neck region. The problem addressed is the difficulty in manually selecting an initial seed point for vessel segmentation, which is time-consuming and prone to variability. The method automates the initial steps while retaining human oversight for accuracy. The process begins by analyzing a medical image composed of multiple slices to automatically detect anatomical landmarks and the corresponding slices where these landmarks appear. These landmarks are used to determine which slices are most relevant for locating the target blood vessel, based on known positional relationships between the landmarks and the vessel. The system then narrows down the search area to these relevant slices, allowing a user to manually select the seed point within this constrained set. This semi-automated approach reduces the time and effort required for seed selection while ensuring accuracy through human input. The method improves efficiency by leveraging automated landmark detection and positional relationships to guide the user to the most likely regions for seed selection, minimizing the need for extensive manual searching. This is particularly useful in complex anatomical regions like the head and neck, where vessel structures can be intricate and difficult to isolate.
6. The method of claim 5 , wherein the landmarks comprise at least one of the lungs, trachea, brain, skull, or segmented blood vessels.
This invention relates to medical imaging and anatomical landmark detection, specifically improving the accuracy of identifying and segmenting key anatomical structures in medical images. The problem addressed is the difficulty in precisely locating and segmenting critical anatomical landmarks such as the lungs, trachea, brain, skull, or segmented blood vessels in imaging data, which is essential for diagnostic and treatment planning. The method involves analyzing medical images to detect and segment these landmarks, enhancing the reliability of subsequent medical analyses. The process includes preprocessing the image data to improve clarity and contrast, followed by applying advanced image processing techniques to identify and delineate the specified anatomical structures. The segmented landmarks are then used to assist in further medical imaging tasks, such as disease detection, surgical planning, or radiation therapy. The invention ensures that the detected landmarks are accurately positioned and segmented, reducing errors in medical assessments. This method is particularly useful in fields like radiology, oncology, and neurology, where precise anatomical mapping is crucial for effective diagnosis and treatment.
7. A method for fully automated segmentation of a segment of a blood vessel of a subject in a medical image comprising volumetric data, comprising: automatically identifying a plurality of circular components in the medical image; automatically segmenting the circular components in parallel planes of the volumetric data; and for each of the circular components, automatically identifying corresponding circular components from the circular components in adjacent planes to define a contiguous segment of corresponding circular components spanning a plurality of the planes; wherein the contiguous segment defines a segment of a blood vessel.
This invention relates to automated segmentation of blood vessels in medical imaging, addressing the challenge of accurately identifying and isolating blood vessel structures within volumetric medical data. The method involves a fully automated process to segment a specific segment of a blood vessel from volumetric medical images, such as those obtained from CT or MRI scans. The process begins by automatically detecting multiple circular components within the medical image. These circular components represent cross-sectional views of the blood vessel at different planes within the volumetric data. The method then segments these circular components in parallel planes of the volumetric data, effectively isolating the circular structures at each slice or plane of the image. Next, for each identified circular component, the method automatically identifies corresponding circular components in adjacent planes. By linking these corresponding circular components across multiple planes, the method defines a contiguous segment of the blood vessel. This contiguous segment spans multiple planes, forming a three-dimensional representation of the blood vessel segment. The contiguous segment, composed of the linked circular components, represents the final segmented blood vessel segment. This approach ensures accurate and automated segmentation without manual intervention, improving efficiency and consistency in medical imaging analysis. The method is particularly useful in applications requiring precise vessel segmentation, such as diagnostic imaging, surgical planning, or vascular analysis.
8. The method according to claim 7 , wherein the circular components have a boundary and are selected using a ratio between the length squared of the circular component boundary and an area of the circular component.
The invention relates to image processing techniques for analyzing circular components within an image. The problem addressed is the accurate selection and measurement of circular components in an image, particularly when distinguishing between true circular shapes and other geometric forms. The method involves analyzing circular components by calculating a ratio between the squared length of the boundary of each circular component and the area of the component. This ratio is used to determine whether a component is a true circle or an approximation, improving the accuracy of circular component detection. The method may be applied in various fields such as medical imaging, quality control, and pattern recognition, where precise identification of circular shapes is critical. The selection process ensures that only components meeting specific geometric criteria are identified, reducing false positives and enhancing reliability. The technique may be integrated into automated systems for real-time analysis, improving efficiency and accuracy in applications requiring circular component detection.
9. The method according to claim 7 , wherein the plurality of circular components are identified based on Hounsfield values.
This invention relates to medical imaging, specifically to the analysis of computed tomography (CT) scans for identifying circular components within a scanned object. The problem addressed is the accurate and automated detection of circular structures in CT images, which is challenging due to variations in image quality, noise, and overlapping anatomical features. The method involves processing a CT scan to identify circular components within the scanned object. The circular components are detected based on Hounsfield values, which are numerical measurements of radiodensity in CT imaging. These values help distinguish different materials or tissues within the scan. The method first segments the CT scan data to isolate regions of interest, then applies an algorithm to detect circular shapes within those regions. The detection process uses Hounsfield values to refine the identification of circular components, ensuring accuracy by filtering out non-circular or irrelevant structures. The method may also include additional steps such as filtering the detected circular components based on size, shape, or density thresholds to further improve accuracy. This approach enhances the reliability of automated analysis in medical imaging, particularly for applications like tumor detection, vascular analysis, or structural assessment in CT scans. The use of Hounsfield values ensures that the identified circular components are physiologically relevant, reducing false positives and improving diagnostic confidence.
Unknown
January 5, 2021
Browse 5M+ US patents with plain-English claim translations and AI-generated analysis.